© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 31647
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Haggadah" and related terms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    odÃŃ
    -0.07
    /UIKit
    -0.07
    ãĥĥãĥģ
    -0.07
     erken
    -0.07
    aldi
    -0.07
    inel
    -0.07
    ment
    -0.07
    MENT
    -0.07
    lém
    -0.07
    ments
    -0.07
    POSITIVE LOGITS
    leta
    0.07
    ity
    0.07
    icle
    0.06
    obb
    0.06
    235
    0.06
     tong
    0.05
    ubs
    0.05
     cust
    0.05
    ubbo
    0.05
    122
    0.05
    Activations Density 0.015%

    No Known Activations